Using Machine Learning to estimate the impact of ports and cruise ship traffic on urban air quality: The case of Barcelona. (May 2021)

• Record Type: Journal Article
• Authors: Fabregat, Alexandre; Vázquez, Lluís; Vernet, Anton
• Is Part Of: Environmental modelling & software. Volume 139(2021)
• Publication Date: 2021-05
• Subjects: Urban air pollution -- Cruise ships -- Generalized boosted regression models -- Machine learning; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2021.104995
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Maritime activity is known to increase pollutant concentration levels in neighboring cities. In major touristic destinations, the singular need of cruise liners to keep supplying energy to on-board services and amenities while docked, has raised concerns about this industry contribution to pollutant emissions. To estimate the impact of port activities and that exclusively due to cruises, classical approaches would rely on atmospheric dispersion models. Although these tools retain the underlying physics, lack of details on background flow state and emission inventories limits their predictive capabilities. Using historical data on pollutant concentration, meteorology and traffic intensity at specific locations across the city of Barcelona, it was found that predictions of local pollutant concentration by the present Machine Learning tool are more accurate than those provided by the CALIOPE-Urban-v1.0 in our test cases. Estimated air quality impact due to cruise ships is shown to be limited in comparison to overall Port effects. Highlights: Machine Learning is proposed as an alternative to classical dispersion models. Working dataset build from pollutant concentration, weather and traffic intensity. ML local predictions found to be more accurate than those from standard approaches. Main features explaining pollutant concentration variability are identified. Cruise ship activity impact on air quality of Barcelona metro area is quantified.